A Method and Device for Discovering Abnormal Calls Based on Communication Behavior Information Entropy
A discovery method and information entropy technology, applied in the field of abnormal call discovery based on information entropy of communication behavior, can solve problems such as low accuracy and misjudgment, and achieve the effect of good discovery effect and practical value
Active Publication Date: 2021-06-18
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention aims at the phenomenon of low precision and misjudgment in traditional abnormal call discovery, and needs to constantly re-excavate diversified features for different targets; a large number of samples and test parameters are required, and there are very difficult problems in practical application , proposes a method and device for discovering abnormal calls based on communication behavior information entropy, starting from multi-dimensional behavior, forming communication behavior information entropy with call behavior quantification, and judging abnormal calls may not be limited to CDR (Call Detail Record, call list data ) and signaling, to solve the problem of abnormal call discovery from the perspective of behavior entropy, which has better discovery effect and practical value
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] The present invention will be further explained in conjunction with the accompanying drawings and specific examples:
[0050] Such as figure 1 As shown, an exception call discovery method based on communication behavior information entropy, including:
[0051] Step S101: Change the multivariate attribute information of the call session to the data source, calculate an exception behavior of each type of behavior;
[0052] Further, the step S101 includes:
[0053] For a plurality of attributes {A, B, C}, the multi-dimensional behavior {x, y, z} corresponding to the call session (each type of attribute corresponding to 1 behavior), each type of active multivariate properties can have multiple attributes The value is expressed as: {a 1 , A 2 , A 3 ..., A mx }, {B 1 , B 2 , B 3 ..., B my }, {C 1 , C 2 , C 3 ..., C mz }; Time offset quantization value Δa at various types of attribute values i1 ΔB i2 ΔC i3 As an input (ie, the multi-power difference between this call and the last ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the technical field of communication network security protection, and discloses a method and device for discovering abnormal calls based on communication behavior information entropy. The method uses the multi-element attribute information change of a call session as a data source to calculate the abnormal behavior probability increment of each type of behavior ; Then quantify the abnormal probability of the multi-dimensional behavior of the call session according to the abnormal behavior probability increment of each type of behavior; then calculate the communication behavior information entropy of behavior events on each dimension, and calculate the joint communication behavior information entropy of the call session; finally calculate the sliding The change rate of the joint communication behavior information entropy of the call session within the window T, when the change rate is greater than the set threshold, the corresponding call session is considered to be an abnormal call session. The invention can be used to quickly discover abnormal communication behaviors such as telecommunication fraud, and has better discovery effect and practical value.
Description
Technical field [0001] The present invention belongs to the field of communication network security protection, focusing on the abnormal behavior analysis and detection of signaling orders in telecommunications network calls, in particular, involving an exception call discovery method and apparatus based on communication behavior information entropy. Background technique [0002] With the rapid development of communication technology and continuous application, the mobile terminal is centralized in the social life. At present, telecom business is gradually combined with social life, industrial control, smart transportation, etc., in terms of social life, industrial production, national security, more important. The multi-service communication relying on the telecom network infrastructure provides a huge support for people's lives and quality, and also provides a large number of unmects, producing a large number of abnormal calls, such as: Telecom Fraud, advertising marketing, mal...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04W12/121G06Q10/04H04M3/22
CPCH04M3/2281H04M2203/6027
Inventor 陈鸿昶刘树新王凯李星马宏吉立新
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU